Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Bank card number recognition method based on opencv

A recognition method and technology for bank card numbers, applied in character recognition, character and pattern recognition, instruments, etc., can solve the problem of low card number recognition accuracy, and achieve the effect of improving accuracy, ensuring recognition speed, and avoiding interference.

Active Publication Date: 2021-11-09
XIDIAN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the deficiencies in the above-mentioned prior art, and propose a bank card number recognition method based on OpenCV, which is used to solve the technical problem of low accuracy of card number recognition in the prior art

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Bank card number recognition method based on opencv
  • Bank card number recognition method based on opencv
  • Bank card number recognition method based on opencv

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Example 1: Bank card number recognition under strong light conditions.

[0048] refer to figure 1 , a bank card number recognition method based on OpenCV, comprising the following steps:

[0049] Step 1) Preprocessing the bank card image:

[0050] Step 1a) utilize the cvtColor function of OpenCV to carry out gray-scale processing to the color bank card image stored in advance, obtain as follows figure 2The grayscale image shown, from figure 2 It can be seen that the gray level of each pixel in the grayscale image is stored with an 8-bit binary number, so the gray level of each pixel ranges from 0 to 255, and there are 256 gray levels in total. It can reduce the storage space of the image and facilitate the subsequent image processing;

[0051] Step 1b) Judging the uniformity of the illumination intensity of the grayscale image:

[0052] Divide the gray level into three levels of high, medium and low, and calculate the ratio of the pixel points in the left and rig...

Embodiment 2

[0071] Example 2: Bank card number recognition under medium light conditions.

[0072] The other steps of this embodiment are the same as those of Embodiment 1, only step 1) has been adjusted.

[0073] Step 1) Preprocessing the bank card image:

[0074] Step 1a) Use the cvtColor function of OpenCV to grayscale the pre-stored color bank card image to obtain a grayscale image such as Figure 10 shown, from Figure 10 It can be seen that the gray level of each pixel in the grayscale image is stored with an 8-bit binary number, so the gray level of each pixel ranges from 0 to 255, and there are 256 gray levels in total. The storage space of the image can be reduced, and it is beneficial to the subsequent image processing; at the same time, the Figure 10 and figure 2 It can be seen from the comparison that the gray level of the grayscale image under medium light conditions is generally lower than that under strong light conditions, and the visual effect presented is darker; ...

Embodiment 3

[0080] Embodiment 3: Bank card number recognition under weak light conditions.

[0081] The other steps of this embodiment are the same as those of Embodiment 1, only step 1) has been adjusted.

[0082] Step 1) Preprocessing the bank card image:

[0083] Step 1a) Use the cvtColor function of OpenCV to grayscale the pre-stored color bank card image to obtain a grayscale image such as Figure 12 shown, from Figure 12 It can be seen that the gray level of each pixel in the grayscale image is stored with an 8-bit binary number, so the gray level of each pixel ranges from 0 to 255, and there are 256 gray levels in total. It can reduce the storage space of the image, and is beneficial to the subsequent image processing, and at the same time Figure 12 and Figure 10 It can be seen from the comparison that the gray level of the grayscale image under weak light conditions is generally lower than that under medium light conditions, and the visual effect presented is darker;

[0084...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention proposes an OpenCV-based bank card number recognition method, which is used to solve the technical problem of low card number recognition accuracy existing in the prior art. The implementation steps are as follows: first grayscale the bank card image, and then distinguish four situations of strong light, medium light, weak light and uneven light, and use different binarization algorithms for different situations to realize the pre-prediction of the bank card image. Processing; through the method of first expansion and erosion and then contour extraction, the image of the card number area in the binarized image is obtained; the character segmentation and normalization are performed by the column projection method, and the character segmentation of the binarized image of the card number area is realized; through The template matching algorithm implements character recognition on the normalized character image set. The invention belongs to the technical field of digital image processing, and relates to a bank card number recognition method, which can be applied to digital recognition occasions such as license plate recognition, bill number recognition, certificate number recognition and the like.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, and relates to a bank card number recognition method, in particular to a bank card number recognition method based on OpenCV, which can be applied to digital recognition occasions such as license plate recognition, bill number recognition, certificate number recognition and the like. Background technique [0002] With the rise of Internet finance, people need to enter bank card numbers in various terminals and bind bank cards to conduct capital transactions. Record the recognition results. The bank card number recognition method first performs preprocessing such as grayscale and binarization on the bank card image, then locates the bank card number, and finally performs digital recognition on the bank card number. [0003] In August 2017, Dong Yanhua and others published an article entitled Research on Bank Card Number Recognition Algorithms Based on OpenCV in the Journal of Jil...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/20G06K9/34G06K9/38
CPCG06V10/141G06V30/153G06V10/267G06V10/28G06V30/10
Inventor 黄遵祥郑春红郑红
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com